© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22770
    Prev
    Next
    INDEX
    Explanations

    shed light on

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron consistently activates on occurrences of the string “shed” (in any context or compound word).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    
    -3.17
    윔
    -3.14
    蠵
    -2.92
    ჻
    -2.92
     saluti
    -2.92
    黢
    -2.81
    栳
    -2.81
    และ
    -2.81
    𐐪
    -2.80
    簟
    -2.78
    POSITIVE LOGITS
    ’
    3.66
    "
    3.55
    '
    2.84
    即使
    2.72
     
    2.66
    ),
    2.59
    ;
    2.58
    ’,
    2.34
    ,…
    2.25
    ",
    2.23
    Activations Density 0.005%

    No Known Activations